Official vendor OpenAPI document · agent-readyDeveloper ToolsTesting QaapiKey13 EndpointsREST
For Agents
Convert PDFs to CSV, JSON, XML, and images, parse invoices with AI, merge and split documents, and generate or read barcodes from uploaded files.
Use for: I need to convert a PDF to CSV for data extraction, I want to parse an invoice and extract line items, Merge multiple PDF files into one document, Split a PDF into individual pages
Not supported: Does not handle document signing, form filling, or OCR on handwritten text - use for format conversion, structured extraction, and barcode operations only.
PDF.co API provides document processing capabilities including AI-powered invoice parsing, PDF conversion to and from multiple formats (CSV, JSON, XML, HTML, PNG), PDF merge and split operations, barcode generation and reading, and file upload management. The API handles both synchronous processing for small files and asynchronous job-based processing for large documents, with results delivered via URL download links.
Install Jentic One Beta
Connect the PDF.co API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the PDF.co API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fpdf.co%2Fpdf-co" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fpdf.co%2Fpdf-co" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with PDF.co API.
Parse invoices and receipts with AI to extract structured line-item data
Convert PDF documents to CSV, JSON, XML, HTML, and PNG formats
Generate PDF files from HTML content with custom styling
Merge multiple PDF files into a single consolidated document
Split PDF documents into individual pages or page ranges
Generate barcodes in multiple formats (QR, Code128, EAN, UPC)
Read and decode barcodes from images and PDF documents
Use Cases
Patterns agents use PDF.co API for, with concrete tasks.
★ AI Invoice Parsing
Extract structured data from invoices and receipts using AI-powered document understanding. The POST /ai-invoice-parser endpoint accepts a PDF or image URL and returns parsed fields including vendor name, invoice number, date, line items with quantities and amounts, tax totals, and payment terms. This eliminates manual data entry for accounts payable automation and expense management workflows.
Upload an invoice PDF via POST /file/upload, then parse it via POST /ai-invoice-parser with the uploaded file URL to extract vendor name, invoice number, and line items
PDF Format Conversion
Convert PDF documents to machine-readable formats for downstream processing. The API supports conversion to CSV (for tabular data), JSON (for structured extraction), XML (for system integration), HTML (for web display), and PNG (for image rendering). Each conversion endpoint accepts a source URL and returns a download link for the converted output.
Convert a PDF containing a data table to CSV format via POST /pdf/convert/to/csv with the source URL and return the download link for the resulting CSV file
Document Assembly and Splitting
Merge multiple PDF files into a single document or split large PDFs into smaller files. The POST /pdf/merge2 endpoint accepts an array of source URLs and produces a combined PDF. POST /pdf/split separates a document by page ranges. These operations enable document workflow automation for contracts, reports, and multi-part submissions.
Merge three PDF files by providing their URLs to POST /pdf/merge2 and return the download URL for the combined document
AI Agent Document Processing via Jentic
AI agents use the PDF.co API through Jentic to parse invoices, convert documents, and extract data without managing API keys directly. Agents search by intent, receive typed schemas for document operations, and execute calls with Jentic handling the x-api-key header injection. This enables automated document workflows in accounting, legal, and data pipeline contexts.
Search Jentic for 'parse invoice from PDF', load the schema for POST /ai-invoice-parser, and execute with the invoice URL to extract structured payment data
Key Endpoints
13 endpoints — pdf.
METHOD
PATH
DESCRIPTION
POST
/ai-invoice-parser
Parse invoices with AI extraction
POST
/pdf/convert/to/csv
Convert PDF to CSV format
POST
/pdf/convert/to/json
Convert PDF to JSON format
POST
/pdf/convert/from/html
Generate PDF from HTML
POST
/pdf/merge2
Merge multiple PDFs into one
POST
/pdf/split
Split PDF into pages
POST
/barcode/generate
Generate a barcode image
POST
/barcode/read/from/url
Read barcodes from an image URL
POST
/ai-invoice-parser
Parse invoices with AI extraction
POST
/pdf/convert/to/csv
Convert PDF to CSV format
POST
/pdf/convert/to/json
Convert PDF to JSON format
POST
/pdf/convert/from/html
Generate PDF from HTML
POST
/pdf/merge2
Merge multiple PDFs into one
POST
/pdf/split
Split PDF into pages
POST
/barcode/generate
Generate a barcode image
POST
/barcode/read/from/url
Read barcodes from an image URL
Jentic AI Readiness Score
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
P
PDF.co API
- AI-Aware (B)67/100
100
Foundational Compliance63
Developer Experience & Jentic Compatibility48
AI-Readiness & Agent Experience94
Agent Usability50
Security100
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.0
Show dimension breakdown
100
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: A+Signals: 4
98%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
100%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
100%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
63
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: B-Signals: 4
0%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
50%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
48
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: D+Signals: 4
43%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
100%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
50%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
50
Security
Trust, risk posture, and security compliance.
Grade: C-Signals: 1
50%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
100
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: A+Signals: 1
100%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the PDF.co API by hand means managing the x-api-key header and mapping source URL and output format parameters across conversion, extraction, and barcode calls yourself. Through Jentic you install once, import PDF.co from the API Directory, store the API key once, and your agent calls it.
Permission scoping
PDF.co carries its source files and options in the request body, so scope the agent by the operations it needs, such as converting a PDF to CSV or JSON or reading a barcode. You choose that set, so operations like merge, split, or invoice parsing are not included unless you add them.
Credential isolation
Your PDF.co API key is stored once, encrypted, by your own Jentic One instance and injected into the x-api-key header at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'convert a PDF to a spreadsheet' or 'read a barcode from a URL', and Jentic returns the matching PDF.co operation with its input schema specifying source URL and output format so the agent calls the right endpoint without reading the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using PDF.co API through Jentic.
What authentication does the PDF.co API use?
The PDF.co API uses an API key passed in the x-api-key header. You obtain your key from the PDF.co dashboard after registration. Through Jentic, this API key is stored encrypted and injected into every request automatically so agents never handle the raw key.
Can I extract table data from PDFs with the PDF.co API?
Yes. POST /pdf/convert/to/csv extracts tabular data from PDF documents and returns it as a downloadable CSV file. For structured extraction with row and column awareness, POST /pdf/convert/to/json provides JSON output with positional data for each text element.
What are the rate limits for the PDF.co API?
PDF.co rate limits depend on your subscription plan. Free plans allow 100 API credits per month with a limit of 1 concurrent request. Paid plans provide higher credit allocations and up to 10 concurrent requests. Each endpoint call consumes 1 credit regardless of file size.
How do I parse an invoice through Jentic?
Search Jentic for 'parse invoice PDF', load the schema for POST /ai-invoice-parser, and execute with the invoice file URL. Jentic handles the x-api-key injection and returns the extracted fields including vendor, invoice number, line items, and totals in a structured response.
Does PDF.co support asynchronous processing for large files?
Yes. For large documents, you can include an async parameter in your request. The API returns a job ID immediately, and you poll POST /job/check with that ID to monitor progress. When complete, the response includes the download URL for the processed output.
Can I limit what my agent is allowed to do with the PDF.co API?
Yes. Because you run Jentic One yourself, your own rules decide which PDF.co operations and credentials your agent can use. Since PDF.co passes its source files and options in the request body, you scope the agent to just the operations it needs, such as converting a PDF to CSV or JSON with POST /pdf/convert/to/csv or reading a barcode with POST /barcode/read/from/url. Operations you leave out, like merge via POST /pdf/merge2, split, or invoice parsing via POST /ai-invoice-parser, stay unavailable to the agent unless you add them.
GET STARTED